📰 Story

v0.1.74

New Features Hook event streaming : Added include_hook_events option to ClaudeAgentOptions . When set, hook events (PreToolUse, PostToolUse, Stop, etc.) are emitted by the CLI and yielded from the message stream as HookEventMessage , matching the TypeScript SDK's includeHookEvents ( #917 ) Defer hook decision : Added support for the "defer" hook decision in PreToolUseHookSpecificOutput.permissionDecision and new DeferredToolUse dataclass on ResultMessage.deferred_tool_use , bringing parity with the TypeScript SDK's deferred tool use round trip ( #865 ) Strict MCP config : Added strict_mcp_config option to ClaudeAgentOptions . When True , the CLI only uses MCP servers passed via mcp_servers , ignoring project, user, and global MCP configurations for fully deterministic server sets ( #915 ) Permission context enrichment : Added decision_reason , blocked_path , title , display_name , and description fields to ToolPermissionContext , enabling richer permission prompts in can_use_tool callbacks ( #909 ) updatedToolOutput for post-tool hooks : Added updatedToolOutput to PostToolUseHookSpecificOutput for replacing any tool's output before it reaches the model, not just MCP tools ( #911 ) xhigh effort level : Added "xhigh" to the effort Literal on ClaudeAgentOptions and AgentDefinition , an Opus 4.7-specific level that falls back to high on other models ( #914 ) Subprocess cleanup on parent exit : Registered an atexit handler to terminate live CLI subprocesses when the parent process